The Problem

AI-generated code often works locally but misses team-specific review expectations:

Corbat helps by giving agents your team's standards before implementation and by providing validation tools before review or handoff.

Quick Start

1. Add to your MCP config:

{
  "mcpServers": {
    "corbat": {
      "command": "npx",
      "args": ["-y", "@corbat-tech/coding-standards-mcp"]
    }
  }
}

2. Config file location:

Complete setup guide for common MCP-compatible tools

3. Done. Corbat can auto-detect your stack and return matching standards.

Zero overhead. Corbat runs locally and adds ~50ms to detect your stack. After that, it's just context for the AI.

Fully customizable. Don't like a rule? Override it in .corbat.json. Jump to customization →

See It In Action

You: "Create a user registration service"

Without Corbat, you get:

class UserService {
  private users: Map<string, User> = new Map();

  register(name: string, email: string, password: string) {
    if (!name || !email || !password) throw new Error('Invalid input');
    const user = { id: crypto.randomUUID(), name, email, password };
    this.users.set(user.id, user);
    return user;
  }
}
// ✗ Hardcoded storage  ✗ Password in plain text  ✗ Generic error  ✗ No tests

With Corbat, you get:

// Domain
interface UserRepository {
  save(user: User): Promise<void>;
  findByEmail(email: string): Promise<User | null>;
}

class EmailAlreadyExistsError extends Error {
  constructor(email: string) {
    super(`Email already registered: ${email}`);
  }
}

// Application
class RegisterUserUseCase {
  constructor(
    private readonly repository: UserRepository,
    private readonly hasher: PasswordHasher
  ) {}

  async execute(input: RegisterUserInput): Promise<User> {
    const existing = await this.repository.findByEmail(input.email);
    if (existing) throw new EmailAlreadyExistsError(input.email);

    const user = User.create({
      ...input,
      password: await this.hasher.hash(input.password)
    });
    await this.repository.save(user);
    return user;
  }
}
// ✓ Repository interface  ✓ Password hashing  ✓ Custom error  ✓ Testable

// Test included
describe('RegisterUserUseCase', () => {
  const repository = { save: vi.fn(), findByEmail: vi.fn() };
  const hasher = { hash: vi.fn() };
  const useCase = new RegisterUserUseCase(repository, hasher);

  beforeEach(() => vi.clearAllMocks());

  it('should hash password before saving', async () => {
    repository.findByEmail.mockResolvedValue(null);
    hasher.hash.mockResolvedValue('hashed_password');

    await useCase.execute({ name: 'John', email: 'john@test.com', password: 'secret' });

    expect(hasher.hash).toHaveBeenCalledWith('secret');
    expect(repository.save).toHaveBeenCalledWith(
      expect.objectContaining({ password: 'hashed_password' })
    );
  });

  it('should reject duplicate emails', async () => {
    repository.findByEmail.mockResolvedValue({ id: '1', email: 'john@test.com' });

    await expect(
      useCase.execute({ name: 'John', email: 'john@test.com', password: 'secret' })
    ).rejects.toThrow(EmailAlreadyExistsError);
  });
});

This is the kind of structure Corbat asks agents to consider before handoff.

What Corbat Provides

Corbat provides these guardrails before generation and validation checks during iteration:

Code Quality

Architecture

Error Handling

Security-Oriented Checks

Benchmark Results v3.0

We evaluated Corbat across 15 scenarios in 6 languages. The primary benchmark report is mixed and should be read honestly: Corbat won 1/15 scenarios by the original aggregate score, while an alternative value analysis found stronger results for code compactness and maintainability.

What The Data Supports

The strongest observed signal is that Corbat-guided outputs are often smaller and more focused:

This is not enough to claim universal quality improvement. It is evidence that standards context can reduce over-generation in some workflows.

Value Metrics

The value report reweights the same dataset toward efficiency and maintainability:

📊 Detailed value analysis

Security: No Benchmark Pattern Findings

Every scenario was analyzed using pattern checks inspired by OWASP Top 10 categories. This is not a replacement for SAST, DAST, dependency scanning, manual review, or threat modeling.

• No SQL/NoSQL injection patterns detected
• No XSS patterns detected
• No hardcoded credentials detected
• Input validation patterns present at boundaries
• Error messages did not expose stack traces in the benchmark samples

Languages & Patterns Tested

📖 Full benchmark methodology · Value analysis

Built-in Profiles

Corbat auto-detects your stack and applies the right standards:

Auto-detection: Corbat reads pom.xml, package.json, go.mod, Cargo.toml, etc.

When to Use Corbat

When Corbat Might Not Be Needed

• Quick prototypes where quality doesn't matter
• One-off scripts you'll throw away
• Learning projects where you want to make mistakes

Customize

Option 1: Interactive Setup

npx corbat-init

Detects your stack and generates a .corbat.json with sensible defaults.

Option 2: Manual Configuration

Create .corbat.json in your project root:

{
  "profile": "java-spring-backend",
  "architecture": {
    "pattern": "hexagonal",
    "layers": ["domain", "application", "infrastructure", "api"]
  },
  "quality": {
    "maxMethodLines": 20,
    "maxClassLines": 200,
    "minCoverage": 80
  },
  "rules": {
    "always": [
      "Use records for DTOs",
      "Prefer Optional over null"
    ],
    "never": [
      "Use field injection",
      "Catch generic Exception"
    ]
  }
}

Option 3: Use a Template

Browse 14 ready-to-use templates for Java, Python, Node.js, React, Go, Rust, and more.

How It Works

┌─────────────┐     ┌─────────────┐     ┌─────────────┐
│ Your Prompt │────▶│ Corbat MCP  │────▶│ AI + Rules  │
└─────────────┘     └──────┬──────┘     └─────────────┘
                          │
           ┌──────────────┼──────────────┐
           ▼              ▼              ▼
    ┌────────────┐ ┌────────────┐ ┌────────────┐
    │ 1. Detect  │ │ 2. Load    │ │ 3. Inject  │
    │   Stack    │ │  Profile   │ │ Guardrails │
    └────────────┘ └────────────┘ └────────────┘
     pom.xml        hexagonal      max 20 lines
     package.json   + DDD          + interfaces
     go.mod         + SOLID        + custom errors

Corbat does not modify AI output. It supplies context, standards, profiles, and validation feedback so agents can align with your review expectations.

Important: Actual code quality depends on the model, host tool, prompt, repository context, tests, and human review. Treat Corbat as a policy and verification layer, not as a guarantee of production readiness.

Documentation

{ "mcpServers": { "corbat": { "command": "npx", "args": ["-y", "@corbat-tech/coding-standards-mcp"] }}}